Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 2084
    Prev
    Next
    INDEX
    Explanations

    phrases related to capturing attention through visual cues

    oai_token-act-pair · gpt-3.5-turbo

    references to attention and visual perception

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĪĴ
    -0.73
    idia
    -0.69
    borg
    -0.69
    seek
    -0.68
    chairs
    -0.67
    pres
    -0.67
    lists
    -0.63
    join
    -0.63
    Panel
    -0.63
    enhagen
    -0.62
    POSITIVE LOGITS
     attention
    1.16
     glimpse
    0.90
     eye
    0.83
     breath
    0.83
    eye
    0.81
     attent
    0.80
     whiff
    0.80
     brunt
    0.79
     glimps
    0.76
     itch
    0.76
    Activations Density 0.135%

    No Known Activations